End-to-End Generation of City-Scale Vectorized Maps by Crowdsourced Vehicles

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Feng, Zebang, Fan, Miao, Liu, Bao, Xu, Shengtong, Xiong, Haoyi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909686084665344
author Feng, Zebang
Fan, Miao
Liu, Bao
Xu, Shengtong
Xiong, Haoyi
author_facet Feng, Zebang
Fan, Miao
Liu, Bao
Xu, Shengtong
Xiong, Haoyi
contents High-precision vectorized maps are indispensable for autonomous driving, yet traditional LiDAR-based creation is costly and slow, while single-vehicle perception methods lack accuracy and robustness, particularly in adverse conditions. This paper introduces EGC-VMAP, an end-to-end framework that overcomes these limitations by generating accurate, city-scale vectorized maps through the aggregation of data from crowdsourced vehicles. Unlike prior approaches, EGC-VMAP directly fuses multi-vehicle, multi-temporal map elements perceived onboard vehicles using a novel Trip-Aware Transformer architecture within a unified learning process. Combined with hierarchical matching for efficient training and a multi-objective loss, our method significantly enhances map accuracy and structural robustness compared to single-vehicle baselines. Validated on a large-scale, multi-city real-world dataset, EGC-VMAP demonstrates superior performance, enabling a scalable, cost-effective solution for city-wide mapping with a reported 90\% reduction in manual annotation costs.
format Preprint
id arxiv_https___arxiv_org_abs_2507_08901
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle End-to-End Generation of City-Scale Vectorized Maps by Crowdsourced Vehicles
Feng, Zebang
Fan, Miao
Liu, Bao
Xu, Shengtong
Xiong, Haoyi
Robotics
High-precision vectorized maps are indispensable for autonomous driving, yet traditional LiDAR-based creation is costly and slow, while single-vehicle perception methods lack accuracy and robustness, particularly in adverse conditions. This paper introduces EGC-VMAP, an end-to-end framework that overcomes these limitations by generating accurate, city-scale vectorized maps through the aggregation of data from crowdsourced vehicles. Unlike prior approaches, EGC-VMAP directly fuses multi-vehicle, multi-temporal map elements perceived onboard vehicles using a novel Trip-Aware Transformer architecture within a unified learning process. Combined with hierarchical matching for efficient training and a multi-objective loss, our method significantly enhances map accuracy and structural robustness compared to single-vehicle baselines. Validated on a large-scale, multi-city real-world dataset, EGC-VMAP demonstrates superior performance, enabling a scalable, cost-effective solution for city-wide mapping with a reported 90\% reduction in manual annotation costs.
title End-to-End Generation of City-Scale Vectorized Maps by Crowdsourced Vehicles
topic Robotics
url https://arxiv.org/abs/2507.08901